Improving Coevolutionary Search for Optimal Multiagent Behaviors
Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. Pages 653-659.
Abstract
Evolutionary computation is a useful technique for learning behaviors in multiagent systems. Among the several types of evolutionary computation, one natural and popular method is to coevolve multiagent behaviors in multiple, cooperating populations. Recent research has suggested that coevolutionary systems may favor stability rather than performance in some domains. In order to improve upon existing methods, this paper examines the idea of modifying traditional coevolution, biasing it to search for maximal rewards. We introduce a theoretical justification of the improved method and present experiments in three problem domains. We conclude that biasing can help coevolution find better results in some multiagent problem domains.
@inproceedings{ijcai2003p96,
title = {Improving Coevolutionary Search for Optimal Multiagent Behaviors},
author = {Panait, Liviu and Wiegand, R. Paul and Luke, Sean},
booktitle = {Proceedings of the Eighteenth International Joint Conference on
Artificial Intelligence, {IJCAI-03}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Georg Gottlob},
pages = {653--659},
year = {2003},
url = {https://ijcai.org/proceedings/2003/96},
}
TY - CPAPER TI - Improving Coevolutionary Search for Optimal Multiagent Behaviors AU - Panait, Liviu AU - Wiegand, R. Paul AU - Luke, Sean T2 - Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03 PB - International Joint Conferences on Artificial Intelligence PY - 2003 SP - 653 EP - 659 UR - https://ijcai.org/proceedings/2003/96 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
